mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 13:33:37 +00:00
community: better support of pathlib paths in document loaders (#18396)
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
This commit is contained in:
@@ -2,7 +2,7 @@ import functools
|
||||
import logging
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Iterator
|
||||
from typing import Any, Dict, Iterator, Union
|
||||
|
||||
import yaml
|
||||
from langchain_core.documents import Document
|
||||
@@ -23,7 +23,10 @@ class ObsidianLoader(BaseLoader):
|
||||
DATAVIEW_INLINE_PAREN_REGEX = re.compile(r"\((\w+)::\s*(.*)\)", re.MULTILINE)
|
||||
|
||||
def __init__(
|
||||
self, path: str, encoding: str = "UTF-8", collect_metadata: bool = True
|
||||
self,
|
||||
path: Union[str, Path],
|
||||
encoding: str = "UTF-8",
|
||||
collect_metadata: bool = True,
|
||||
):
|
||||
"""Initialize with a path.
|
||||
|
||||
|
Reference in New Issue
Block a user